alistair23-linux/net/netfilter/ipset/ip_set_hash_mac.c

174 lines
4.6 KiB
C
Raw Normal View History

/* Copyright (C) 2014 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
/* Kernel module implementing an IP set type: the hash:mac type */
#include <linux/jhash.h>
#include <linux/module.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/errno.h>
#include <linux/if_ether.h>
#include <net/netlink.h>
#include <linux/netfilter.h>
#include <linux/netfilter/ipset/ip_set.h>
#include <linux/netfilter/ipset/ip_set_hash.h>
#define IPSET_TYPE_REV_MIN 0
#define IPSET_TYPE_REV_MAX 0
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
IP_SET_MODULE_DESC("hash:mac", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_hash:mac");
/* Type specific function prefix */
#define HTYPE hash_mac
/* Member elements */
struct hash_mac4_elem {
/* Zero valued IP addresses cannot be stored */
union {
unsigned char ether[ETH_ALEN];
__be32 foo[2];
};
};
/* Common functions */
static inline bool
hash_mac4_data_equal(const struct hash_mac4_elem *e1,
const struct hash_mac4_elem *e2,
u32 *multi)
{
return ether_addr_equal(e1->ether, e2->ether);
}
static inline bool
hash_mac4_data_list(struct sk_buff *skb, const struct hash_mac4_elem *e)
{
if (nla_put(skb, IPSET_ATTR_ETHER, ETH_ALEN, e->ether))
goto nla_put_failure;
return false;
nla_put_failure:
return true;
}
static inline void
hash_mac4_data_next(struct hash_mac4_elem *next,
const struct hash_mac4_elem *e)
{
}
#define MTYPE hash_mac4
#define HOST_MASK 32
#define IP_SET_EMIT_CREATE
#define IP_SET_PROTO_UNDEF
#include "ip_set_hash_gen.h"
/* Zero valued element is not supported */
static const unsigned char invalid_ether[ETH_ALEN] = { 0 };
static int
hash_mac4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_mac4_elem e = { { .foo[0] = 0, .foo[1] = 0 } };
struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
/* MAC can be src only */
if (!(opt->flags & IPSET_DIM_ONE_SRC))
return 0;
if (skb_mac_header(skb) < skb->head ||
(skb_mac_header(skb) + ETH_HLEN) > skb->data)
return -EINVAL;
ether_addr_copy(e.ether, eth_hdr(skb)->h_source);
if (memcmp(e.ether, invalid_ether, ETH_ALEN) == 0)
return -EINVAL;
return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
}
static int
hash_mac4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_mac4_elem e = { { .foo[0] = 0, .foo[1] = 0 } };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
int ret;
if (tb[IPSET_ATTR_LINENO])
*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
if (unlikely(!tb[IPSET_ATTR_ETHER]))
return -IPSET_ERR_PROTOCOL;
ret = ip_set_get_extensions(set, tb, &ext);
if (ret)
return ret;
ether_addr_copy(e.ether, nla_data(tb[IPSET_ATTR_ETHER]));
if (memcmp(e.ether, invalid_ether, ETH_ALEN) == 0)
return -IPSET_ERR_HASH_ELEM;
return adtfn(set, &e, &ext, &ext, flags);
}
static struct ip_set_type hash_mac_type __read_mostly = {
.name = "hash:mac",
.protocol = IPSET_PROTOCOL,
.features = IPSET_TYPE_MAC,
.dimension = IPSET_DIM_ONE,
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
.create = hash_mac_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
[IPSET_ATTR_PROBES] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
},
.adt_policy = {
[IPSET_ATTR_ETHER] = { .type = NLA_BINARY,
.len = ETH_ALEN },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_LINENO] = { .type = NLA_U32 },
[IPSET_ATTR_BYTES] = { .type = NLA_U64 },
[IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
[IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING,
.len = IPSET_MAX_COMMENT_SIZE },
[IPSET_ATTR_SKBMARK] = { .type = NLA_U64 },
[IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 },
[IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 },
},
.me = THIS_MODULE,
};
static int __init
hash_mac_init(void)
{
return ip_set_type_register(&hash_mac_type);
}
static void __exit
hash_mac_fini(void)
{
netfilter: ipset: Introduce RCU locking in hash:* types Three types of data need to be protected in the case of the hash types: a. The hash buckets: standard rcu pointer operations are used. b. The element blobs in the hash buckets are stored in an array and a bitmap is used for book-keeping to tell which elements in the array are used or free. c. Networks per cidr values and the cidr values themselves are stored in fix sized arrays and need no protection. The values are modified in such an order that in the worst case an element testing is repeated once with the same cidr value. The ipset hash approach uses arrays instead of lists and therefore is incompatible with rhashtable. Performance is tested by Jesper Dangaard Brouer: Simple drop in FORWARD ~~~~~~~~~~~~~~~~~~~~~~ Dropping via simple iptables net-mask match:: iptables -t raw -N simple || iptables -t raw -F simple iptables -t raw -I simple -s 198.18.0.0/15 -j DROP iptables -t raw -D PREROUTING -j simple iptables -t raw -I PREROUTING -j simple Drop performance in "raw": 11.3Mpps Generator: sending 12.2Mpps (tx:12264083 pps) Drop via original ipset in RAW table ~~~~~~~~~~~~~~~~~~~~~~~~~~~ Create a set with lots of elements:: sudo ./ipset destroy test echo "create test hash:ip hashsize 65536" > test.set for x in `seq 0 255`; do for y in `seq 0 255`; do echo "add test 198.18.$x.$y" >> test.set done done sudo ./ipset restore < test.set Dropping via ipset:: iptables -t raw -F iptables -t raw -N net198 || iptables -t raw -F net198 iptables -t raw -I net198 -m set --match-set test src -j DROP iptables -t raw -I PREROUTING -j net198 Drop performance in "raw" with ipset: 8Mpps Perf report numbers ipset drop in "raw":: + 24.65% ksoftirqd/1 [ip_set] [k] ip_set_test - 21.42% ksoftirqd/1 [kernel.kallsyms] [k] _raw_read_lock_bh - _raw_read_lock_bh + 99.88% ip_set_test - 19.42% ksoftirqd/1 [kernel.kallsyms] [k] _raw_read_unlock_bh - _raw_read_unlock_bh + 99.72% ip_set_test + 4.31% ksoftirqd/1 [ip_set_hash_ip] [k] hash_ip4_kadt + 2.27% ksoftirqd/1 [ixgbe] [k] ixgbe_fetch_rx_buffer + 2.18% ksoftirqd/1 [ip_tables] [k] ipt_do_table + 1.81% ksoftirqd/1 [ip_set_hash_ip] [k] hash_ip4_test + 1.61% ksoftirqd/1 [kernel.kallsyms] [k] __netif_receive_skb_core + 1.44% ksoftirqd/1 [kernel.kallsyms] [k] build_skb + 1.42% ksoftirqd/1 [kernel.kallsyms] [k] ip_rcv + 1.36% ksoftirqd/1 [kernel.kallsyms] [k] __local_bh_enable_ip + 1.16% ksoftirqd/1 [kernel.kallsyms] [k] dev_gro_receive + 1.09% ksoftirqd/1 [kernel.kallsyms] [k] __rcu_read_unlock + 0.96% ksoftirqd/1 [ixgbe] [k] ixgbe_clean_rx_irq + 0.95% ksoftirqd/1 [kernel.kallsyms] [k] __netdev_alloc_frag + 0.88% ksoftirqd/1 [kernel.kallsyms] [k] kmem_cache_alloc + 0.87% ksoftirqd/1 [xt_set] [k] set_match_v3 + 0.85% ksoftirqd/1 [kernel.kallsyms] [k] inet_gro_receive + 0.83% ksoftirqd/1 [kernel.kallsyms] [k] nf_iterate + 0.76% ksoftirqd/1 [kernel.kallsyms] [k] put_compound_page + 0.75% ksoftirqd/1 [kernel.kallsyms] [k] __rcu_read_lock Drop via ipset in RAW table with RCU-locking ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ With RCU locking, the RW-lock is gone. Drop performance in "raw" with ipset with RCU-locking: 11.3Mpps Performance-tested-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
2015-06-13 09:29:56 -06:00
rcu_barrier();
ip_set_type_unregister(&hash_mac_type);
}
module_init(hash_mac_init);
module_exit(hash_mac_fini);